A command that rebuilds a documentation dashboard from a project's docs-cockpit.yaml configuration file. It writes an HTML dashboard and a JSON state file.

Rendering the project's documentation modules, concepts, and system documents into a viewable dashboard, with an optional debug mode.

It avoids manually rebuilding the dashboard after documentation or configuration changes and reports validation warnings and item counts.

render — Command by Guohao1020

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/guohao1020/docs-cockpit/render

Clone the repo

git clone --depth 1 https://github.com/Guohao1020/docs-cockpit

Or install docs-cockpit, the plugin that ships this one along with the rest of its 3 skills, 5 commands, 1 hook.

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 563 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00024	$0.00563
Opus 5	$0.00012	$0.00282
Sonnet 5	$0.00005	$0.00113
Haiku 4.5	$0.00002	$0.00056

Measured 3d ago against content hash a8f566205052, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

render scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/render.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explicit invocation of the docs-cockpit render pipeline. Use this when the user wants to force a render immediately without going through natural-language workflow detection.

Note: docs-cockpit build (the pre-1.0 name) was removed in 1.1 — use render.

Steps

Locate the config. Look for docs-cockpit.yaml in the current working directory. If a path argument was passed after the slash command (/docs-cockpit:render configs/preview.yaml), use that path instead.
Bootstrap if missing. If no config exists, don't fail — hand off to the docs-cockpit-build skill's bootstrap workflow (it'll diagnose the doc layout and write a starter config first).

Run the render.

docs-cockpit render -c <config-path>
# Add --debug if the user explicitly asked to debug

Surface key output lines:
- [OK] Built <path> — confirm the HTML wrote
- state: <path> — confirm state.json wrote (≥0.1.1 required)
- [WARN] frontmatter: ... — frontmatter validation warnings
- [!] docs-cockpit X.Y.Z available — version banner; if seen, suggest invoking /docs-cockpit:update
Report counts. Pull the modules: N | concepts: N | system_docs: N line and surface it. Also surface the module status · done=X in-progress=Y ... line and the overall progress: N% line so the user can see at-a-glance summary.
Suggest next move based on output:
- All clean → "open docs/index.html to verify"
- Frontmatter warnings → suggest consulting references/schema.md for the offending field
- Version banner → suggest /docs-cockpit:update
- 0 items (no modules / concepts / system_docs visible) → diagnose paths.repo and scan paths (usually the cause), suggest --debug rerun

Don't do these

Don't rewrite the user's yaml without permission. If docs-cockpit.yaml has problems, point them at the right group / field to edit, don't silently fix.
Don't open the HTML in a browser automatically (some users are in remote / headless environments).
Don't pass --no-version-check unless the user explicitly asks — the version banner is a feature.

Read the full file on GitHub · 41 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago First seen · 41 lines · 24 tokens per session scan A a8f566205052

Subscribe to this mod's changes

render is a command published in the GitHub repository Guohao1020/docs-cockpit (2 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 563 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Documents claude-code claude-code-plugin claude-skills dashboard frontmatter kanban

render

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Steps

Don't do these

What this file has done since we first saw it

Other commands, from other repositories

export

export

release

autobot-stop

autobot-result

compile_paper